{"ID":2864303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23832","arxiv_id":"2509.23832","title":"LORT: Locally Refined Convolution and Taylor Transformer for Monaural Speech Enhancement","abstract":"Achieving superior enhancement performance while maintaining a low parameter count and computational complexity remains a challenge in the field of speech enhancement. In this paper, we introduce LORT, a novel architecture that integrates spatial-channel enhanced Taylor Transformer and locally refined convolution for efficient and robust speech enhancement. We propose a Taylor multi-head self-attention (T-MSA) module enhanced with spatial-channel enhancement attention (SCEA), designed to facilitate inter-channel information exchange and alleviate the spatial attention limitations inherent in Taylor-based Transformers. To complement global modeling, we further present a locally refined convolution (LRC) block that integrates convolutional feed-forward layers, time-frequency dense local convolutions, and gated units to capture fine-grained local details. Built upon a U-Net-like encoder-decoder structure with only 16 output channels in the encoder, LORT processes noisy inputs through multi-resolution T-MSA modules using alternating downsampling and upsampling operations. The enhanced magnitude and phase spectra are decoded independently and optimized through a composite loss function that jointly considers magnitude, complex, phase, discriminator, and consistency objectives. Experimental results on the VCTK+DEMAND and DNS Challenge datasets demonstrate that LORT achieves competitive or superior performance to state-of-the-art (SOTA) models with only 0.96M parameters, highlighting its effectiveness for real-world speech enhancement applications with limited computational resources.","short_abstract":"Achieving superior enhancement performance while maintaining a low parameter count and computational complexity remains a challenge in the field of speech enhancement. In this paper, we introduce LORT, a novel architecture that integrates spatial-channel enhanced Taylor Transformer and locally refined convolution for e...","url_abs":"https://arxiv.org/abs/2509.23832","url_pdf":"https://arxiv.org/pdf/2509.23832v1","authors":"[\"Junyu Wang\",\"Zizhen Lin\",\"Tianrui Wang\",\"Meng Ge\",\"Longbiao Wang\",\"Jianwu Dang\"]","published":"2025-09-28T12:12:21Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[\"Transformer\"]","has_code":false}